• Journal of KIISE:Software and Applications
• /
• v.32 no.7
• /
• pp.581-591
• /
• 2005

Collaborative filtering systems have problems involving sparsity and the provision of recommendations by making correlations between only two users' preferences. These systems recommend items based only on the preferences without taking in to account the contents of the items. As a result, the accuracy of recommendations depends on the data from user-rated items. When users rate items, it can be expected that not all users ran do so earnestly. This brings down the accuracy of recommendations. This paper proposes a collaborative recommendation method for extracting typical group preferences using user-item matrix optimization and user profiles in collaborative tittering systems. The method excludes unproven users by using entropy based on data from user-rated items and groups users into clusters after generating user profiles, and then extracts typical group preferences. The proposed method generates collaborative user profiles by using association word mining to reflect contents as well as preferences of items and groups users into clusters based on the profiles by using the vector space model and the K-means algorithm. To compensate for the shortcoming of providing recommendations using correlations between only two user preferences, the proposed method extracts typical preferences of groups using the entropy theory The typical preferences are extracted by combining user entropies with item preferences. The recommender system using typical group preferences solves the problem caused by recommendations based on preferences rated incorrectly by users and reduces time for retrieving the most similar users in groups.

• The KIPS Transactions:PartB
• /
• v.10B no.3
• /
• pp.273-280
• /
• 2003

Recommender System can help users to find products to Purchase. A representative method for recommender systems is collaborative filtering (CF). It predict products that user may like based on a group of similar users. User information is based on user's ratings for products and similarities of users are measured by ratings. As user is increasing tremendously, the performance of the pure collaborative filtering is lowed because of high dimensionality and scarcity of data. We consider the effect of dimension deduction in collaborative filtering to cope with scarcity of data experimentally. We suggest that SVD improves the performance of collaborative filtering in comparison with pure collaborative filtering.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.183-188
• /
• 2021

Collaborative filtering based recommender systems are currently indispensable function of commercial systems in various fields, being a useful service by providing customized products that users will prefer. However, there is a high possibility that the prediction of preferrable products is inaccurate, when the user's rating data are insufficient. In order to overcome this drawback, this study suggests a stepwise method for prediction of product ratings. If the application conditions of the prediction method corresponding to each step are not satisfied, the method of the next step is applied. To evaluate the performance of the proposed method, experiments using a public dataset are conducted. As a result, our method significantly improves prediction and precision performance of collaborative filtering systems employing various conventional similarity measures and outperforms performance of the previous methods for solving rating data sparsity.

• Fashion & Textile Research Journal
• /
• v.6 no.6
• /
• pp.815-824
• /
• 2004

In academic and/or practitioner literature, the assortment planning for fashion sensitive products is rarely systematically studied, and organized in an objective format. The purpose of this study was to develop a suggested assortment planning model for women's clothing retail buyers by integrating a conceptual assortment planning model and a practical-use assortment planning model, which are also developed in this study. In developing the conceptual model, this research categorized and organized the pieces of assortment planning activities illustrated in available literature. In developing the practical-use model, ten women's dress buyers from department stores and specialty stores were interviewed. The contents of the interview dictation were classified and summarized by concepts and variables. The summary was validated by the interviewees and recontextualized for the practical-use model. Five experts compared the conceptual and practical-use models, adjusted the discrepancies, and integrated into the suggested model. In addition, a questionnaire asking review of all functional activities of the suggested model was sent to interviewees to ascertain its validity. As the result, assortment planning process was determined at abstract level as the following: (a) recognize problem, (b) search for information, (c) evaluate qualitative value of product, (d) evaluate quantitative value of product, (e) plan product selection, and (f) plan sales.

• Management & Information Systems Review
• /
• v.38 no.2
• /
• pp.67-81
• /
• 2019

In accordance with K-IFRS 1109, financial instruments are classified to amortized cost (AC), fair value through other comprehensive income (FVOCI) and fair value through profit or loss (FVPL). And disposal gains are prohibited to be recirculated for net income when FVOCI financial instruments would be sold in the future, so-called recirculation prohibition. This research investigates whether accumulated other comprehensive income of available-for sale financial assets(AFS) under K-IFRS 1039, could affect reclassified amounts to the FVPL securities from the AFS securities. Also, this study investigates the effects of the reported income on the reclassified FVPL, because CEOs are likely to try earnings management when net income is predicted to be less than target or is low, comparing other firms. As a result of empirical analysis, first, I find that accumulated other comprehensive income of the AFS has a positive impact on the reclassified FVPL. Second, level of reporting income has no significant impact on the reclassified FVPL. Third, interaction effects are significantly positive on the firms which have more other comprehensive income and less level of reported income. Fourth, the effects of the bank and securities are more distinct than those of the manufactures. This study is the first research to investigate earnings management through AFS at the timing of the first adoption of K-IFRS 1109. Empirical results of this study provide evidence of earnings management on the reclassification of FVPL which gives meaningful implications to regulators, academic researchers and auditors.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.2
• /
• pp.222-226
• /
• 2010

With the continuously increasing volume of e-commerce transactions, it is now popular to buy some products and to evaluate them on the World Wide Web. The product reviews are very useful to customers because they can make better decisions based on the indirect experiences obtainable through these reviews. However, since online shopping malls do not provide ranking results, it is not easy for users to read all the relevant review documents effectively. Product reviews include subjective and emotional opinions. Thus, the review search is different from the general web search in terms of ranking strategy. In this paper, we propose an effective method of ranking the reviews that can reflect user's intention by using opinion mining techniques. The proposed method analyzes product reviews with query words, and sentimental polarity of subjective opinions. Through diverse experiments, we show that our proposed method outperforms conventional ones.

• Proceedings of the Costume Culture Conference
• /
• 2003.09a
• /
• pp.85-86
• /
• 2003

의복은 비언어적 상징으로서 의사를 전달하는 무언의 언어로 이용되어 사람들은 의복을 통해 자기를 나타내며 동시에 다른 사람을 지각하고 평가하게 되는데 이러한 역할은 현대사회에 와서 더욱 강조되었다. 따라서 소비자들은 이미지라는 감정적ㆍ주관적인 요소로써 의류상품을 평가, 구매하는 경우가 많다. 이에 본 연구에서는 여자 대학생을 대상으로 자신이 생각하는 자기 이미지에 따른 실제 착용하는 의복이미지, 추구하는 의복이미지와 의복구매행동을 조사하는 것을 목적으로 하며 의류산업체에서 의류상품개발을 위한 자료를 제공하고자 하였다. (중략)

• Journal of Intelligence and Information Systems
• /
• v.3 no.1
• /
• pp.1-12
• /
• 1997

파생금융상품이란 주식이나 채권과 같은 기준자산에 대해서 발행되는 2차 금융상품으로써 기존의 재무이론에서는 수리적 모형에 기반을 둔 가격결정모형을 이용하여 가치를 평가하였다. 그러나 이러한 전통적인 가격결정모형은 복잡한 현실세계를 단순화시키기 위한 제반 가정을 요구하기 때문에 이러한 가정이 현실에 부적합한 경우에는 모형가격이 실제가격으로부터 커다란 괴리를 갖게 된다. 본 연구에서는 전통적인 가격결정방법의 단점을 극복할 수 있는 자료 의존적인 인공신경망기법을 제시하고 대표적인 파생금융상품인 국내 전환사채의 가격결정에 적용해 봄으로써 그 가능성을 제시하였다. 인공신경망기법을 전환사채의 가격결정에 적용한 결과 전통적 가격결정방법에 비해 평균절대오차를 70%정도 줄일 수 있다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2002.05a
• /
• pp.953-959
• /
• 2002

계절유행상품의 수요는 연중 성수기가 길지 않고 매년 유행과 제품디자인 변화가심한 경향이 있어 수요예측에 과거의 판매정보의 유용성이 크지 않다. 성수기 초반의 수요가 연간 수요결정에 매우 중요하며 후반부수요가 급격히 감소하는 특성이 있다. 반면 이월상품의 잔존가치가 매우 낮지만 매출마진이 높아 수요예측의 정확도에 따라 수익률이 큰 영향을 받는다. 이러한 이유로 기존의 수요예측방법을 계절상품에 적용하기에 무리가 따르며 예측오차의 비용이 매우 커서 계절상품 관리에 이용할 수 없다. 본 연구에서 성수기를 하위기간으로 구분하여 시즌 초반부 수요발생시점을 측정하여 초반부 기간별수요량을 구하고 이를 근거로 기간 누적수요비율을 quantile regression에 의거 추정하여 기간별 수요량과 전제 수요량을 예측하는 방법을 제시하고 모의자료를 사용하여 이 모형의 우수성을 평가하였다.

• The monthly packaging world
• /
• s.273
• /
• pp.101-109
• /
• 2016

굿디자인(GOOD DESINE)이란 산업통상자원부가 주최하고 한국디자인진흥원의 주관 아래, 산업디자인진흥법에 의거하여 상품의 외관, 기능, 재료, 경제성 등을 종합적으로 심사하여 디자인의 우수성이 인정된 상품에 GOOD DESINE 마크를 부여하는 제도로 1985년부터 매년 시행해 오고 있다. GD마크 선정제란 우수한 디자인 상품개발을 장려하여 국가 경쟁력을 확보하고 국민 삶의 질 향상에 기여하는 것을 목표로 하고 있으며, 나아가 유니버설디자인, 서비스디자인, 전통시장, 산업단지 디자인을 고도화(우수디자인 선정, 장려 등)함으로써 사회적 문제해결과 지속가능한 창조경제를 실현하는데 그 의의가 있다. 선정 대상 품목으로는 제품디자인, 환경디자인, 소재표면처리디자인, 패션디자인, 포장디자인, 커뮤니케이션디자인, 건축디자인 패션디자인으로 대통령상 1점을 비롯해 국무총리상, 대상, 최우수상 등을 시상하고 있다. 굿디자인 상품은 향후 조달청이 시행하는 우수제품선정 및 물품구매 적격심사 시 우대되며, 중소기업청이 시행하는 수출유망중소기업지정 및 수출기업화 사업평가시 우대받을 수 있다. 마크사용에 있어 호주 디자인상(AIDA)과의 상호인증으로 마크 부착이 가능하다. 본 고에서는 2015년 우수디자인(GD)으로 선정된 제품 가운데 생활 포장 및 산업포장 부문 수상작들과 일부 선정된 제품들을 살펴본다.